literature-screening@0.1.0: benchmark test

Record

block:        literature-screening@0.1.0
test:         benchmark
material:     Search and screening of a published review, compared with its list of included studies
model:        a named model and version
runs:         10 in total, 1 failed, 0 aborted
result:       Recall of included studies 0.91; precision 0.62. Most misses were conference papers without abstracts.
evaluator:    Noor Haddad, CRediT role "validation"
scope:        One review in one field; recall in other fields is untested.
date:         2027-03-03

The record counts failed and aborted runs, because reporting only successful runs overstates performance.

@software{noorhaddad2027evaluationofliteraturesc,
  title   = {Evaluation of literature-screening@0.1.0 (benchmark)},
  author  = {Noor Haddad},
  year    = {2027},
  note    = {e2er evaluation record. Persistent identifier planned},
  url     = {https://e2er.org/evaluations/ev-0003}
}